Age | Commit message (Collapse) | Author | |
---|---|---|---|
2023-03-30 | ggml : fix NEON signs (close #620, #622) | Georgi Gerganov | |
2023-03-30 | Fix GGML_F32Cx8_STORE in AVX without F16C path (#619) | slaren | |
2023-03-29 | ci : re-enable AVX512 testing (Windows-MSVC) (#584) | anzz1 | |
* CI: Re-enable AVX512 testing (Windows-MSVC) Now with 100% less base64 encoding * plain __cpuid is enough here | |||
2023-03-29 | ggml : init time on first ggml_init() call | Georgi Gerganov | |
2023-03-29 | llama : fix compile warnings when reading the vocab | Georgi Gerganov | |
2023-03-29 | ggml : add ARM_NEON dequantize_row_q4_1() | Georgi Gerganov | |
2023-03-29 | ggml : add ARM_NEON quantize_row_q4_1() | Georgi Gerganov | |
2023-03-29 | ggml : add ARM_NEON ggml_vec_dot_q4_1() | Georgi Gerganov | |
2023-03-29 | rename convert_ggml_to_pth.py -> convert-ggml-to-pth.py (#600) | Pavol Rusnak | |
to match filenames of other converters | |||
2023-03-29 | Create chat-13B.bat (#592) | Thérence | |
* Create chat-13B.bat Same script than chat-13B.sh, but for windows users. Tested and working on windows 10/11 v 22H2 * Apply suggestions from code review --------- Co-authored-by: anzz1 <anzz1@live.com> | |||
2023-03-29 | readme : fix typos | Georgi Gerganov | |
2023-03-29 | readme : add GPT4All instructions (close #588) | Georgi Gerganov | |
2023-03-29 | py : add GPT4All conversion script | Georgi Gerganov | |
For now: copy-paste Too much time for me to deduplicate the python code | |||
2023-03-29 | llama : use the same threshold for OpenBLAS and ggml thread limiting (#577) | Maël Kerbiriou | |
2023-03-29 | add example of re-act pattern (#583) | Tobias Lütke | |
* add example of re-act pattern * spelling... * fixed whitespace in reverse prompt issue | |||
2023-03-29 | Fix GCC warning about binary literal (#595) | anzz1 | |
0b10101010 -> 0xAA /* 0b10101010 */ | |||
2023-03-29 | Fix typo in llama.h (#593) | anzz1 | |
2023-03-28 | Enable Fused-Multiply-Add (FMA) and F16C/CVT16 vector extensions on MSVC (#375) | anzz1 | |
* Enable Fused-Multiply-Add (FMA) instructions on MSVC __FMA__ macro does not exist in MSVC * Enable F16C/CVT16 vector extensions on MSVC __F16C__ macro does not exist in MSVC, but is implied with AVX2/AVX512 * MSVC cvt intrinsics * Add __SSE3__ macro for MSVC too because why not even though it's not currently used for anything when AVX is defined | |||
2023-03-28 | CI: fix subdirectory path globbing (#546) | anzz1 | |
- Changes in subdirectories will now be detecter properly - (Windows-MSVC) AVX512 tests temporarily disabled | |||
2023-03-28 | llama : fix linkage with mingw (#551) | anzz1 | |
* Revert 7e53955 (#542) Still needs to be fixed properly * Fix linking on mingw32 | |||
2023-03-28 | ggml : add AVX2 implementation of quantize_row_q4_1 (#515) | slaren | |
* Add AVX2 implementation of quantize_row_q4_1 * Actually use AVX2 * Make quantize_row_q4_1 static Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> | |||
2023-03-28 | py : add temporary script to convert old ggml files to newer version (#539) | thement | |
Co-authored-by: Jakub Horak <jakub.horak@ibawizard.net> | |||
2023-03-28 | py : add capabiliy to convert from ggml back to torch or hf format for ↵ | Tai Duc Nguyen | |
further consumption/training/finetuning (#403) | |||
2023-03-28 | ggml : refactor quantized processing functions (#509) | Stephan Walter | |
* Refactor quantized processing functions * ggml : minor --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> | |||
2023-03-28 | py : removed unused `model` variable and verified that the code functions ↵ | DooWoong Lee (David) | |
correctly with `vocab_only` setting. Also confirmed that the code works as expected after running with reduced memory usage due to deletion of no-longer-needed variable. (#547) | |||
2023-03-28 | ci : make ctest verbose, hopefully we see what is wrong with the sanitizer | Georgi Gerganov | |
2023-03-28 | tests : free llama context at the end of the test | Georgi Gerganov | |
2023-03-28 | all : be more strict about converting float to double (#458) | Stephan Walter | |
* Be more strict about converting float to double * Test equivalence of round, SILU implementations Test module is commented out in CMakeLists.txt because the tests may take a long time, depending on how much the compiler optimizes. * Fix softmax in perplexity.cpp * all : prefer float over double where appropriate * perplexity : add <cmath> --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> | |||
2023-03-28 | deploy : add a Package.swift for SwiftPM support (#393) | Jed Fox | |
* Add a Package.swift for SwiftPM support * Swap from exclusions to allowlist | |||
2023-03-28 | ggml : introduce structs for the q4 data blocks (#356) | Stephan Walter | |
* Introduce structs for the q4 data blocks * ggml : rename quant struct variables + fix ARM_NEON --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> | |||
2023-03-28 | gitignore : add "embedding" | Georgi Gerganov | |
2023-03-28 | Check the existence of f16_model_path_base in quantize.py (#574) | dotpy314 | |
Co-authored-by: Jincheng Miao <jincheng.miao@gmail.com> | |||
2023-03-28 | Fix usage of F16C intrinsics in AVX code (#563) | slaren | |
* Fix usage of F16C intrinsics in AVX code when F16C is not defined | |||
2023-03-28 | main.cpp fixes, refactoring (#571) | anzz1 | |
- main: entering empty line passes back control without new input in interactive/instruct modes - instruct mode: keep prompt fix - instruct mode: duplicate instruct prompt fix - refactor: move common console code from main->common | |||
2023-03-28 | Add embedding example to Makefile (#540) | RJ Adriaansen | |
2023-03-27 | Fix missing ggml link in cmake for examples/* on w64-mingw32 (#542) | Marco Matthies | |
2023-03-26 | ci: add debug build to sanitizer build matrix (#527) | Erik Scholz | |
2023-03-26 | Fix undefined variables in debug build, remove unused variables (#531) | Stephan Walter | |
2023-03-26 | Add support for linux/arm64 platform during Docker Builds (#514) | Juan Calderon-Perez | |
* Add support for linux/arm64 platform * Add platform to versioned builds | |||
2023-03-26 | Update README and comments for standalone perplexity tool (#525) | Stephan Walter | |
2023-03-26 | [main] fix infinite generation (-n == -1) (#523) | anzz1 | |
2023-03-26 | Add logo to README.md | Georgi Gerganov | |
2023-03-26 | Exit from interactive mode if input stream is bad (#491) | Harald Fernengel | |
Allow exiting the interactive prompt also with CTRL-D on Unix and CTRL-Z on Windows. | |||
2023-03-26 | CI: Run other sanitizer builds even if one fails (#511) | anzz1 | |
applies only to sanitizer builds so they wont be cancelled | |||
2023-03-25 | Clarify console output in convert-pth-to-ggml.py (#512) | jp-x-g | |
"Processing part 1 of 3" instead of "Processing part 0" | |||
2023-03-25 | CMake / CI additions (#497) | anzz1 | |
* CMake: Add AVX512 option * CI: Add AVX/AVX512 builds (Windows) (AVX512 tests can only be run when the worker happens to support it, building works anyway) * CMake: Fix sanitizer linkage ( merged #468 ) * CI: Add sanitizer builds (Ubuntu) * CI: Fix release tagging (change @zendesk/action-create-release to @anzz1/action-create-release until upstream PR Added commitish as input zendesk/action-create-release#32 is merged) | |||
2023-03-25 | (Windows) Set console to UTF-8 on init (#420) | anzz1 | |
Sets console codepage to 65001 (CP_UTF8) on start for both input and output, should fix problems with UTF-8 characters. | |||
2023-03-25 | Fix colors enabling on WIN32 | Georgi Gerganov | |
2023-03-25 | If n_predict == -1, generate forever | Georgi Gerganov | |
2023-03-25 | Inifinite generation via context swapping (#71) | Georgi Gerganov | |